BESSER-PEARL
OrganizationAgent Skills for BESSER — deep BESSER knowledge for AI coding agents: UML class modeling, code generators, troubleshooting, and contributor workflows.
Categories
Indexed Skills (4)
besser-dev
Contributor guide for developing BESSER itself (https://github.com/BESSER-PEARL/BESSER). Use this skill whenever the user is working *inside* the BESSER source tree — adding a new generator (the most common contribution), adding a new metamodel or sub-DSL under `besser/BUML/metamodel/`, writing pytest tests for generators or metamodels, writing JSON↔BUML converters for the web editor, building Sphinx documentation under `docs/source/`, registering a generator in `SUPPORTED_GENERATORS`, or preparing a pull request to BESSER. Trigger on phrases like "add a new generator", "register in the web editor", "GeneratorInterface", "json_to_buml", "buml_to_json", "write tests for my generator", "build the docs", "open a PR to BESSER", or any work that touches `besser/generators/`, `besser/BUML/metamodel/`, `besser/utilities/web_modeling_editor/`, or `tests/`. Prefer this skill over besser-user when the user is contributing *to* BESSER rather than *using* BESSER to build something else.
besser-generators
Operational reference for BESSER code generators — covers per-generator options, generated file layout, regeneration/overwrite behavior, safe customization patterns, template overrides, and debugging generation failures. Use this skill whenever the user is configuring or running a BESSER generator (PythonGenerator, PydanticGenerator, SQLAlchemyGenerator, SQLGenerator, BackendGenerator, RESTAPIGenerator, DjangoGenerator, WebAppGenerator, ReactGenerator, BAFGenerator, QiskitGenerator, JSONSchemaGenerator, RDFGenerator, TerraformGenerator, PytorchGenerator, TFGenerator, FlutterGenerator, JavaGenerator), wondering "where does the output go", "will my edits survive regeneration", "how do I add custom endpoints to a generated FastAPI app", or "how do I switch the database dialect". Trigger on questions about generator parameters (`http_methods`, `nested_creations`, `dbms`, `containerization`, `backend_type`, `shots`, `generation_mode`), generated file paths, template overrides, or how to extend generated code witho
besser-troubleshooting
Diagnose and fix BESSER errors fast. Use this skill whenever the user is staring at a Python traceback, ImportError, ModuleNotFoundError, ValueError, TypeError, AttributeError, jinja2.TemplateNotFoundError, subprocess.CalledProcessError, or any other failure originating from BESSER (besser.BUML, besser.generators, besser.utilities). Covers installation failures (`pip install besser` errors, native dependency build failures for psycopg2/pyodbc/oracledb, Python version mismatches, Windows venv path quirks), import errors (`String` vs `StringType`, missing `bocl==0.3.1`, `antlr4-python3-runtime` version mismatch), model construction errors (spaces or hyphens in names, duplicate enum literals, invalid multiplicities, generalization-to-self, more than one is_id per class), generator crashes (Invalid DBMS, Django subprocess failures, missing GUIModel for WebApp, silent SQLGenerator failures, invalid Qiskit backend), Docker and deployment problems (port conflicts, docker-compose vs docker compose, missing system lib
besser-user
Build software with BESSER, the low-code model-driven platform. Use this skill whenever the user is creating a B-UML domain model (classes, attributes, associations, enumerations, generalizations), running any BESSER generator (Django, FastAPI, SQLAlchemy, Pydantic, React, WebApp, BAF, Qiskit, etc.), modeling state machines or chatbot agents, designing GUI models for web apps, or working with the BESSER web editor at editor.besser-pearl.org. Trigger on imports from `besser.BUML` or `besser.generators`, mentions of B-UML, DomainModel, BinaryAssociation, GUIModel, or any BESSER generator class — even if the user does not say "BESSER" by name. Prefer this skill over generic Python, Django, or FastAPI guidance whenever the project uses BESSER for modeling. For per-generator deep dives (output paths, options, customization patterns), defer to the besser-generators skill; for errors and diagnostics, defer to besser-troubleshooting.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.